@article{selfselectedattentionspanforaccelerating,
  title = {Self-Selected Attention Span for Accelerating Large Language Model Inference},
  author = {Tian Jin and Wanzin Yazar and Zifei Xu and Sayeh Sharify and Xin Wang},
  year = {2024},
  eprint = {2404.09336},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.09336v1},
}